Inferring Adjective Hypernyms with Language Models to Increase the Connectivity of Open English Wordnet
This work addresses a connectivity issue in a key linguistic resource, but it is incremental as it adapts existing methods to a specific domain.
The paper tackled the problem of missing hypernymy links for adjectives in Open English Wordnet by developing a new resource and fine-tuning large language models to predict these links, achieving results that adapt the TaxoLLaMa methodology to this task.
Open English Wordnet is a key resource published in OntoLex-lemon as part of the linguistic linked open data cloud. There are, however, many links missing in the resource, and in this paper, we look at how we can establish hypernymy between adjectives. We present a theoretical discussion of the hypernymy relation and how it differs for adjectives in contrast to nouns and verbs. We develop a new resource for adjective hypernymy and fine-tune large language models to predict adjective hypernymy, showing that the methodology of TaxoLLaMa can be adapted to this task.